What GPU do I need to run XiaomiMiMo/MiMo-V2-Flash?

309.8B parameters, published in F8_E4M3. View on Hugging Face

309.8B
Parameters
F8_E4M3
Native precision
MiMoV2FlashForCausalLM
Architecture
text-generation
Pipeline

MiMo-V2-Flash is published by XiaomiMiMo on Hugging Face, with 88,038 downloads and 749 likes to date. It's a MiMoV2FlashForCausalLM model built for text-generation, published natively in F8_E4M3.

VRAM required & cheapest live GPU fit

Required VRAM = weight size at each precision times a flat 1.2 overhead for activations and fragmentation. The KV-cache grows with context and is not in that factor; it is listed per model below where the architecture is published. Full formula and assumptions: methodology.

PrecisionWeight sizeRequired VRAMCheapest live fitGPUs neededEst. $/hr (full fit)
FP8 (native)288.5 GB346.2 GBAMD MI300X2$5.26/hr
INT4 (quantized)144.3 GB173.1 GBAMD MI300X1$2.63/hr
cheaper alt.RTX A50008$1.41/hr

A GPU is only matched to a row if its hardware supports that precision, and the primary recommendation is always a single-GPU fit when one exists.

INT4 requires a quantized checkpoint actually published for this model, check its Hugging Face page before relying on this row.

Cheapest way to run MiMo-V2-Flash at its published (F8_E4M3) precision: 2× AMD MI300X, at $2.63/hr per GPU ($5.26/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.

MiMo-V2-Flash: KV cache by context length

The KV cache is the memory the attention layers hold for every token of context, on top of the weights. It is not part of the flat 1.2x overhead in the table above, grows with context length and with every concurrent request, and is why a long-context deployment needs more VRAM than the table shows.

KV-cache size for MiMo-V2-Flash is not published for this architecture, so no figure is shown.

MiMo-V2-Flash: common questions

Can MiMo-V2-Flash run on a single GPU?

No. At FP8 (native) it needs 346.2 GB of VRAM, more than a single 32 GB desktop card holds. The cheapest capable card in the live feed is a 192.0 GB AMD MI300X, and it takes 2 of them.

Is MiMo-V2-Flash already quantized?

Yes. It is published in FP8, one byte per parameter, so the 346.2 GB figure is already a quantized footprint rather than a full-precision one. Only INT4 goes below it, at 173.1 GB. A GPU without FP8 tensor cores cannot run it as published, which is why cards here are matched on precision support and not on VRAM alone.

How many GPUs do I need to run MiMo-V2-Flash?

2 at FP8 (native). It needs 346.2 GB of VRAM and the cheapest capable live offer is a 192.0 GB AMD MI300X, so 2 of them come to $5.26/hr in total.

Does quantizing MiMo-V2-Flash lower the GPU bill?

Yes. At FP8 (native) the cheapest live fit is 2 AMD MI300X cards at $5.26/hr. At INT4 (quantized) it drops to one AMD MI300X at $2.63/hr, provided a quantized checkpoint exists for it.

Weight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.

More MiMo V2 models

All 4 MiMo V2 models: VRAM and GPU requirements

Alternatives at this size

Other models for text-generation within about a third of MiMo-V2-Flash's 309.8B parameters, from other model lines.

More on MiMo-V2-Flash

Related reading: AMD MI300X pricing and specs, How much VRAM you need for LLMs, Serving LLMs with vLLM, vLLM vs TensorRT-LLM vs SGLang, and Best GPU for LLM inference.

Your own GPU cloud accounts

One console for the GPU clouds you already rent from. Your keys stay on your machine.

$20 a month, flat

Connect your accounts

One console for the GPU clouds you already use.

Connect your accounts for $20 a month, flat. Your provider bills the GPU.

© 2026 Aquanode. All rights reserved.

All trademarks, logos and brand names are the property of their respective owners.